© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 103829
    Prev
    Next
    INDEX
    Explanations

    telling you

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     yourself
    -2.17
     we
    -1.68
    Your
    -1.59
     your
    -1.52
     they
    -1.45
     Yourself
    -1.45
    yourself
    -1.37
     YOURSELF
    -1.37
     youre
    -1.26
     I
    -1.21
    POSITIVE LOGITS
     us
    2.02
     you
    1.59
     vás
    1.54
     вас
    1.49
     him
    1.45
     them
    1.43
     вам
    1.42
     ya
    1.34
     тебе
    1.30
     vám
    1.30
    Activations Density 0.097%

    No Known Activations